Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for improving a call-participant behavior, the method comprising: receiving an intensity data signal and an intensity variation data signal related to an ongoing call; receiving a pitch data signal and a pitch variation data signal related to the ongoing call; receiving a tempo data signal and a tempo variation data signal related to the ongoing call; receiving a channel comparison data signal related to the ongoing call; generating a real-time call progress signal based on the intensity data signal, the intensity variation data signal, the pitch data signal, the pitch variation data signal, the tempo data signal, the tempo variation data signal, and the channel comparison data signal; and sending the real-time call progress signal to a user device.
A method for improving how people behave during a phone call involves analyzing the call in real-time. This is done by receiving data signals related to the call's intensity (loudness), intensity variation, pitch, pitch variation, tempo (speaking rate), tempo variation, and channel comparison (who is talking when). Based on these signals, a "real-time call progress signal" is generated, providing information about the call's dynamics. This signal is then sent to a user device, presumably to provide feedback or insights.
2. The method according to claim 1 , wherein the channel comparison data signal comprises: a talk-over data signal related to the ongoing call; a speaker dominance data signal related to the ongoing call; or a turn-taking data signal related to the ongoing call.
The call improvement method from the previous description includes a detailed analysis of "channel comparison," looking at who's speaking, when, and how. The "channel comparison data signal" specifically analyzes: 1) "talk-over," which detects when someone interrupts or speaks over another person; 2) "speaker dominance," which identifies who is controlling the conversation's flow; and 3) "turn-taking," which analyzes how smoothly participants are exchanging speaking turns. This more granular analysis of channel behaviour is also used to generate the real-time call progress signal sent to the user device.
3. The method according to claim 1 , wherein the method further comprises: receiving an intonation data signal related to the ongoing call; receiving an articulation data signal related to the ongoing call; receiving an accent data signal related to the ongoing call; and receiving an interruption data signal related to the ongoing call.
The call improvement method from the initial description is enhanced by including even more detailed voice analysis. In addition to intensity, pitch, tempo, and channel comparison, the method also receives 1) intonation data (variations in pitch to convey emotion); 2) articulation data (clarity of speech); 3) accent data (distinctive pronunciation patterns); and 4) interruption data (frequency and nature of interruptions). All of these new voice characteristics are incorporated into generating the real-time call progress signal that is sent to the user device.
4. The method according to claim 3 , wherein at least one of: the intonation data signal is determined based on the pitch data signal; the articulation data signal is determined based on at least one of the intensity data signal and the pitch data signal; and the accent data signal is determined based on at least one of the intensity data signal, the pitch data signal, and the tempo data signal.
In the call improvement method described previously, with extra voice data, at least one of the following relationships exists: 1) Intonation data is determined from the pitch data (intonation is a specific use of pitch); 2) Articulation data is determined from intensity and/or pitch data (volume and frequency); and 3) Accent data is determined from intensity, pitch, and/or tempo data (volume, frequency, and rate of speech). This specifies dependencies between new voice elements and base voice elements.
5. The method according to claim 1 , wherein the method further comprises receiving at least one of: a noise data signal related to the ongoing call; a music data signal related to the ongoing call; an interruption data signal related to the ongoing call; and a voice stress data signal related to the ongoing call.
In addition to intensity, pitch, tempo, and channel comparison, the initial call improvement method also receives data signals relating to: 1) noise levels during the call; 2) presence of music; 3) interruption events; and/or 4) voice stress levels. This additional environmental information is used to generate the real-time call progress signal sent to the user device.
6. The method according to claim 5 , wherein at least one of the noise data signal, the music data signal, and the voice stress data signal are determined based on at least one of the intensity data signal, the pitch data signal, and the tempo data signal.
In the call improvement method previously described, which includes noise, music, and voice stress analysis, at least one of these signals is determined based on: 1) intensity data; 2) pitch data; and/or 3) tempo data. This shows that noise, music, or voice stress can be derived from the base audio features that are already being analyzed.
7. The method according to claim 5 , wherein the interruption data signal is based on at least one of the intensity data signal, the pitch data signal, the tempo data signal and the talk-over data signal.
In the call improvement method described previously, which includes interruption detection, the interruption data signal is based on: 1) intensity data; 2) pitch data; 3) tempo data; and/or 4) the "talk-over" data signal (from the channel comparison). This means interruption events are not only explicitly tracked, but can also be inferred or validated from changes in volume, frequency, rate of speech, and who is talking over who.
8. The method according to claim 1 , the method further comprising: generating a conversational balance data signal based on the channel comparison data signal; generating a conversational engagement data signal based on at least one of the channel comparison data signal and a conversational balance data signal; or generating a conversational experience data signal based on at least one of the channel comparison data signal, the conversational balance data signal, and the conversational engagement data signal.
Expanding on the initial call improvement method, which incorporates channel comparison, additional data signals are generated: 1) a "conversational balance" data signal, based on the channel comparison data; 2) a "conversational engagement" data signal, based on the channel comparison data and/or the conversational balance data; and/or 3) a "conversational experience" data signal, based on the channel comparison data, the conversational balance data, and/or the conversational engagement data. These provide successively higher-level abstractions about the interaction.
9. The method according to claim 1 , wherein the real-time call progress signal comprises at least one of: a sensory cue signal and a call progress report signal.
The real-time call progress signal, from the initial call improvement method, includes: 1) a sensory cue signal (a direct, immediate notification); and/or 2) a call progress report signal (a summary of the call's characteristics). The system can provide instant feedback or summarized overviews.
10. The method according to claim 9 , wherein the sensory cue signal comprises at least one of the following: a visual cue, an auditory cue, and a haptic cue.
The sensory cue signal from the previous call improvement method can take various forms: 1) a visual cue (e.g., a color change or icon); 2) an auditory cue (e.g., a beep or tone); and/or 3) a haptic cue (e.g., a vibration). This gives flexibility in how the system provides real-time feedback to the user.
11. The method according to claim 1 , wherein the user device comprises at least one of the following: a human user interface and a supervisor user interface.
In the initial call improvement method, the user device that receives the real-time call progress signal includes: 1) a human user interface (for a call participant); and/or 2) a supervisor user interface (for a manager or observer). The system is designed to give feedback to users and observers of the call.
12. A method for improving a call-participant behavior, the method comprising: receiving a voice analytics signal related to an ongoing call, the voice analytics signal comprising a pitch data signal and a pitch variation signal related to the ongoing call, a tempo data signal and a tempo variation signal related to the ongoing call, and a receiving channel comparison data signal related to the ongoing call; and generating a real-time call progress signal based on the voice analytics signal, wherein the real-time call progress signal comprises at least one of a sensory cue signal and a call progress report signal.
A simplified method for improving phone call behavior analyzes "voice analytics" in real-time. This analytics data includes pitch, pitch variation, tempo, tempo variation, and channel comparison (who is talking). Based on these voice analytics, a "real-time call progress signal" is generated, which can be either a "sensory cue" (immediate feedback) or a "call progress report" (summary of the call).
13. The method according claim 12 , further comprising: sending the sensory cue signal to a human user interface.
The call improvement method using voice analytics, described previously, sends the "sensory cue signal" (immediate feedback) to a human user interface, directly influencing the user during the call.
14. The method according to claim 12 , further comprising: sending the call progress report signal to a human user interface or a supervisor user interface.
The call improvement method using voice analytics, described previously, sends the "call progress report signal" (summary of the call) to either a human user interface or a supervisor user interface, which gives the user or supervisor an overview of the call.
15. The method according to claim 12 , wherein the sensory cue signal comprises at least one of the following: a visual cue, an auditory cue, and a haptic cue.
The sensory cue signal from the call improvement method that uses voice analytics includes: 1) a visual cue; 2) an auditory cue; and/or 3) a haptic cue. This gives flexibility in providing real-time feedback.
16. The method according to claim 12 , wherein the voice analytics signal comprises: an intensity data signal related to the ongoing call; an intensity variation data signal related to the ongoing call; a pitch data signal related to the ongoing call; a pitch variation data signal related to the ongoing call; a pitch confidence data signal related to the pitch data signal; a tempo data signal related to the ongoing call; a tempo variation data signal related to the ongoing call; and a channel comparison data signal related to the ongoing call.
In the call improvement method using voice analytics described previously, the voice analytics signal includes a lot of data: 1) intensity; 2) intensity variation; 3) pitch; 4) pitch variation; 5) pitch confidence (reliability of the pitch detection); 6) tempo; 7) tempo variation; and 8) channel comparison. The analysis is comprehensive and uses a variety of voice characteristics.
17. The method according to claim 16 , wherein the channel comparison data signal comprises: a talk-over data signal related to the ongoing call; a speaker dominance data signal related to the ongoing call; or a turn-taking data signal related to the ongoing call.
In the voice analytics method for call improvement, the channel comparison data signal includes: 1) talk-over detection; 2) speaker dominance detection; and/or 3) turn-taking analysis.
18. A system for improving a call-participant behavior, the system comprising: an intensity determiner that determines an intensity variance and an intensity related to an ongoing call; a pitch determiner that determines a pitch variance and a pitch related to the ongoing call; a pitch confidence determiner that determines a pitch confidence variance and a pitch confidence related to the determined pitch; a tempo determiner that determines a tempo and a tempo variance related to the ongoing call; a channel comparison determiner that compares multiple channels related to the ongoing call and determines a channel comparison data signal; a reporter that generates a real-time call progress signal based on at least one of the intensity, the intensity variance, the pitch, the pitch variance, the pitch confidence, the tempo, the tempo variance and the channel comparison data signal; and an interface that sends the real-time call progress signal to a user device.
A system designed to improve phone call behavior includes the following components: 1) an "intensity determiner" that measures the loudness and changes in loudness; 2) a "pitch determiner" that measures the frequency and changes in frequency; 3) a "pitch confidence determiner" that assesses the reliability of the pitch measurements; 4) a "tempo determiner" that measures the speaking rate and changes in speaking rate; 5) a "channel comparison determiner" that analyzes who is speaking when; 6) a "reporter" that generates a real-time call progress signal based on the combined data; and 7) an "interface" that sends the call progress signal to a user device.
19. The method according to claim 18 , wherein the channel comparison determiner comprises: a talk-over determiner that determines talk-over related to the ongoing call; a speaker dominance determiner that determines speaker dominance related to the ongoing call; and a turn-taking determiner that determines turn-taking related to the ongoing call.
The call improvement system from the previous description includes these specific channel comparison components: 1) a "talk-over determiner" that detects interruptions; 2) a "speaker dominance determiner" that identifies the dominant speaker; and 3) a "turn-taking determiner" that analyzes how smoothly participants exchange speaking turns.
20. The system according to claim 18 , further comprising: a database that stores the real-time call progress signal.
The call improvement system described earlier, which includes voice analysis and real-time feedback, also has a database to store the "real-time call progress signal" for later analysis or reporting.
21. The system according to claim 18 , wherein the real-time call progress signal comprises at least one of: a sensory cue signal and a call progress report signal, wherein the sensory cue signal comprises a visual cue, an auditory cue, or a haptic cue.
The call improvement system described earlier, which includes voice analysis and real-time feedback, generates a "real-time call progress signal" that contains either a "sensory cue signal" (immediate feedback, such as visual, auditory, or haptic cues) or a "call progress report signal" (a summarized overview of the call).
22. The system according to claim 18 , further comprising: an intonation determiner that determines an intonation variance and an intonation related to the ongoing call; an articulation determiner that determines an articulation variance and an articulation related to the ongoing call; an accent determiner that determines an accent variance and accent related to the ongoing call; and an interruption determiner that determines an interruption variance and an interruption related to the ongoing call.
Expanding on the call improvement system described previously, which incorporates voice analysis and real-time feedback, also includes: 1) an "intonation determiner" that measures intonation and intonation variation; 2) an "articulation determiner" that measures articulation and articulation variation; 3) an "accent determiner" that measures accent and accent variation; and 4) an "interruption determiner" that measures interruption events and their variation.
23. The system according to claim 22 , wherein at least one of: the intonation is determined based on the pitch; the articulation is determined based on at least one of the intensity and the pitch; and the accent is determined based on at least one of the intensity, the pitch, and the tempo.
In the call improvement system described previously, which includes intonation, articulation, accent, and interruption detection, there are dependencies between parameters: 1) intonation is determined based on pitch; 2) articulation is determined based on intensity and/or pitch; and 3) accent is determined based on intensity, pitch, and/or tempo.
Unknown
November 25, 2014
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.